|---|
| [ View source on GitHub](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/layers/preprocessing/image_preprocessing/random_rotation.py#L14-L246) |
A preprocessing layer which randomly rotates images during training.
Inherits From: [`Layer`](https://www.tensorflow.org/api_docs/python/tf/keras/Layer.md.txt), [`Operation`](https://www.tensorflow.org/api_docs/python/tf/keras/Operation.md.txt)
```python
tf.keras.layers.RandomRotation(
factor,
fill_mode='reflect',
interpolation='bilinear',
seed=None,
fill_value=0.0,
data_format=None,
**kwargs
)
```
### Used in the notebooks
| Used in the guide | Used in the tutorials |
|---|---|
| - [Working with preprocessing layers](https://www.tensorflow.org/guide/keras/preprocessing_layers.md.txt) | - [Image classification](https://www.tensorflow.org/tutorials/images/classification.md.txt) - [Data augmentation](https://www.tensorflow.org/tutorials/images/data_augmentation.md.txt) - [Transfer learning and fine-tuning](https://www.tensorflow.org/tutorials/images/transfer_learning.md.txt) - [Retraining an Image Classifier](https://www.tensorflow.org/hub/tutorials/tf2_image_retraining.md.txt) |
```python
This layer will apply random rotations to each image, filling empty space
according to `fill_mode`.
By default, random rotations are only applied during training.
At inference time, the layer does nothing. If you need to apply random
rotations at inference time, pass `training=True` when calling the layer.
Input pixel values can be of any range (e.g. `[0., 1.)` or `[0, 255]`) and
of integer or floating point dtype.
By default, the layer will output floats.
Note: This layer is safe to use inside a tf.data or `grain` pipeline
(independently of which backend you're using).
Input shape:
3D (unbatched) or 4D (batched) tensor with shape:
`(..., height, width, channels)`, in `"channels_last"` format
Output shape:
3D (unbatched) or 4D (batched) tensor with shape:
`(..., height, width, channels)`, in `"channels_last"` format
Args:
factor: a float represented as fraction of 2 Pi, or a tuple of size 2
representing lower and upper bound for rotating clockwise and
counter-clockwise. A positive values means rotating
counter clock-wise,
while a negative value means clock-wise.
When represented as a single
float, this value is used for both the upper and lower bound.
For instance, `factor=(-0.2, 0.3)`
results in an output rotation by a random
amount in the range `[-20% * 360, 30% * 360]`.
`factor=0.2` results in an
output rotating by a random amount
in the range `[-20% * 360, 20% * 360]`.
fill_mode: Points outside the boundaries of the input are filled
according to the given mode
(one of `{"constant", "reflect", "wrap", "nearest"}`).
- *reflect*: `(d c b a | a b c d | d c b a)`
The input is extended by reflecting about
the edge of the last pixel.
- *constant*: `(k k k k | a b c d | k k k k)`
The input is extended by
filling all values beyond the edge with
the same constant value k = 0.
- *wrap*: `(a b c d | a b c d | a b c d)` The input is extended by
wrapping around to the opposite edge.
- *nearest*: `(a a a a | a b c d | d d d d)`
The input is extended by the nearest pixel.
interpolation: Interpolation mode. Supported values: `"nearest"`,
`"bilinear"`.
seed: Integer. Used to create a random seed.
fill_value: a float represents the value to be filled outside
the boundaries when `fill_mode="constant"`.
data_format: string, either `"channels_last"` or `"channels_first"`.
The ordering of the dimensions in the inputs. `"channels_last"`
corresponds to inputs with shape `(batch, height, width, channels)`
while `"channels_first"` corresponds to inputs with shape
`(batch, channels, height, width)`. It defaults to the
`image_data_format` value found in your Keras config file at
`~/.keras/keras.json`. If you never set it, then it will be
`"channels_last"`.
Example:
```
```python
layer = keras.layers.RandomRotation(bounding_box_format="xyxy")
images = np.random.randint(0, 255, (4, 224, 224, 3), dtype="uint8")
bounding_boxes = {
"boxes": np.array([
[[10, 20, 100, 150], [50, 60, 200, 250]],
[[15, 25, 110, 160], [55, 65, 210, 260]],
[[20, 30, 120, 170], [60, 70, 220, 270]],
[[25, 35, 130, 180], [65, 75, 230, 280]],
], dtype="float32"),
"labels": np.array([[0, 1], [1, 2], [2, 3], [0, 3]], dtype="int32")
}
labels = keras.ops.one_hot(
np.array([0, 1, 2, 3]),
num_classes=4
)
segmentation_masks = np.random.randint(0, 3, (4, 224, 224, 1), dtype="uint8")
output = layer(
{
"images": images,
"bounding_boxes": bounding_boxes,
"labels": labels,
"segmentation_masks": segmentation_masks
},
training=True
)
```
| ## Attributes ||
|---|---|
| `input` | Retrieves the input tensor(s) of a symbolic operation. Only returns the tensor(s) corresponding to the *first time* the operation was called. |
| `output` | Retrieves the output tensor(s) of a layer. Only returns the tensor(s) corresponding to the *first time* the operation was called. |
## Methods
### `convert_weight`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/layers/preprocessing/data_layer.py#L153-L159)
```python
convert_weight(
weight
)
```
Convert the weight if it is from the a different backend.
### `from_config`
[View source](https://github.com/keras-team/keras/tree/v3.15.1/keras/src/ops/operation.py#L322-L362)
```python
@classmethod
from_config(
config
)
```
Creates an operation from its config.
This method is the reverse of `get_config`, capable of instantiating the
same operation from the config dictionary.
> [!NOTE]
> **Note:** If you override this method, you might receive a serialized dtype config, which is a `dict`. You can deserialize it as follows:
```python
if "dtype" in config and isinstance(config["dtype"], dict):
policy = dtype_policies.deserialize(config["dtype"])
```
| Args ||
|---|---|
| `config` | A Python dictionary, typically the output of `get_config`. |